Player Detection based on Support Vector Machine in Football Videos

Abstract

An automatic player detection method based on fuzzy decision making one-class SVM is proposed. Detection results of statistical classifier player detection methods are better than rule based player detection methods. However, manually labelled training samples are used in these statistical classifiers based player detection methods. Thus, cost is very important. To resolve this problem, we propose an instinctive player detection method using fuzzy decision making one-class SVM and automatically collected player samples. In this method, one-class SVM (OCSVM) is introduced to train the player detector by drawing lessons from the human object category classification mechanism. Additionally, decision function of OCSVM is improved by dividing the decision value dynamically using the fuzzy decision method, which is able to reduce the detection error caused by the insufficient representativeness of the automatically collected training samples. Finally, a set of criteria is introduced to obtain the training samples automatically, and player detection experiments are performed on these training samples using FD-OCSVM. Experiments show that better detection results are obtained using the proposed method in the scenario of using automatically collected training samples, which improves the automatic degree of player detection.

Occupancy Analysis of the Outdoor Football Fields

“…They imple-mented a one-class SVM technique to detect players on a soccer field. Oneclass SVM has also been reported in [85], where it is followed by a fuzzy c-mean algorithm to facilitate the prediction of data points close to the SVM hyper-plane. In [38], HOG features-based Adaboost algorithm is proposed for player detection on the football field.…”